English
Related papers

Related papers: Regularized Online RLHF with Generalized Bilinear …

200 papers

Hoffman's classical result gives a bound on the distance of a point from a convex and compact polytope in terms of the magnitude of violation of the constraints. Recently, several results showed that Hoffman's bound can be used to derive…

Machine Learning · Computer Science 2019-02-19 Dan Garber

This paper introduces a dual-based algorithm framework for solving the regularized online resource allocation problems, which have potentially non-concave cumulative rewards, hard resource constraints, and a non-separable regularizer. Under…

Machine Learning · Computer Science 2023-07-18 Wanteng Ma , Ying Cao , Danny H. K. Tsang , Dong Xia

Learning of low-rank matrices is fundamental to many machine learning applications. A state-of-the-art algorithm is the rank-one matrix pursuit (R1MP). However, it can only be used in matrix completion problems with the square loss. In this…

Machine Learning · Computer Science 2016-07-28 Quanming Yao , James T. Kwok

We propose new algorithms with provable performance for online binary optimization subject to general constraints and in dynamic settings. We consider the subset of problems in which the objective function is submodular. We propose the…

Optimization and Control · Mathematics 2024-05-03 Antoine Lesage-Landry , Julien Pallage

We study offline constrained reinforcement learning from human feedback with multiple preference oracles. Motivated by applications that trade off performance with safety or fairness, we aim to maximize target population utility subject to…

Machine Learning · Computer Science 2026-04-02 Brenden Latham , Mehrdad Moharrami

We study the online learning with feedback graphs framework introduced by Mannor and Shamir (2011), in which the feedback received by the online learner is specified by a graph $G$ over the available actions. We develop an algorithm that…

Machine Learning · Computer Science 2021-07-21 Liad Erez , Tomer Koren

We obtain essentially tight upper bounds for a strengthened notion of regret in the stochastic linear bandits framework. The strengthening -- referred to as Nash regret -- is defined as the difference between the (a priori unknown) optimum…

Machine Learning · Computer Science 2023-10-04 Ayush Sawarni , Soumybrata Pal , Siddharth Barman

In the stochastic contextual low-rank matrix bandit problem, the expected reward of an action is given by the inner product between the action's feature matrix and some fixed, but initially unknown $d_1$ by $d_2$ matrix $\Theta^*$ with rank…

Machine Learning · Statistics 2024-01-17 Yue Kang , Cho-Jui Hsieh , Thomas C. M. Lee

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in…

Machine Learning · Computer Science 2017-06-20 Lihong Li , Yu Lu , Dengyong Zhou

Self-normalized martingale inequalities lie at the heart of confidence ellipsoids for online least squares and, more broadly, many bandit and reinforcement-learning results. Yet existing vector and scalar results typically rely on bounded…

Machine Learning · Statistics 2026-05-05 Fan Chen , Jian Qian , Alexander Rakhlin , Nikita Zhivotovskiy

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning…

Machine Learning · Computer Science 2012-11-28 Ankan Saha , Prateek Jain , Ambuj Tewari

We consider an online learning problem on a continuum. A decision maker is given a compact feasible set $S$, and is faced with the following sequential problem: at iteration~$t$, the decision maker chooses a distribution $x^{(t)} \in…

Machine Learning · Computer Science 2015-04-30 Walid Krichene

We develop a methodology for constructing confidence sets for parameters of statistical models via a reduction to sequential prediction. Our key observation is that for any generalized linear model (GLM), one can construct an associated…

Statistics Theory · Mathematics 2025-04-24 Eugenio Clerico , Hamish Flynn , Wojciech Kotłowski , Gergely Neu

Recent advancement in online optimization and control has provided novel tools to study online linear quadratic regulator (LQR) problems, where cost matrices are time-varying and unknown in advance. In this work, we study the online linear…

Optimization and Control · Mathematics 2025-07-15 Ting-Jui Chang , Shahin Shahrampour

We introduce a method for policy improvement that interpolates between the greedy approach of value-based reinforcement learning (RL) and the full planning approach typical of model-based RL. The new method builds on the concept of a…

Machine Learning · Statistics 2022-06-20 Shantanu Thakoor , Mark Rowland , Diana Borsa , Will Dabney , Rémi Munos , André Barreto

Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users in order to gain information that will lead to…

Machine Learning · Computer Science 2021-12-28 Manish Raghavan , Aleksandrs Slivkins , Jennifer Wortman Vaughan , Zhiwei Steven Wu

In a low-rank linear bandit problem, the reward of an action (represented by a matrix of size $d_1 \times d_2$) is the inner product between the action and an unknown low-rank matrix $\Theta^*$. We propose an algorithm based on a novel…

Machine Learning · Statistics 2020-10-20 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

Machine Learning · Computer Science 2019-02-08 Chaobing Song , Ji Liu , Han Liu , Yong Jiang , Tong Zhang

We consider the problem of online prediction in a marginally stable linear dynamical system subject to bounded adversarial or (non-isotropic) stochastic perturbations. This poses two challenges. Firstly, the system is in general…

Machine Learning · Computer Science 2020-11-24 Udaya Ghai , Holden Lee , Karan Singh , Cyril Zhang , Yi Zhang

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained…

Computation and Language · Computer Science 2024-12-06 Vishakh Padmakumar , Chuanyang Jin , Hannah Rose Kirk , He He